Artificial Intelligence in Metabolomics for Disease Profiling: A Machine Learning Approach to Biomarker Discovery

Muhammad Danial Ahmad Qureshi; Muhammad Fahid Ramzan; Fatima Amjad; Naeem Haider

doi:10.70749/ijbr.v2i02.146

Authors

Muhammad Danial Ahmad Qureshi University of Management and Technology, Lahore, Punjab, Pakistan.
Muhammad Fahid Ramzan University of Punjab, Lahore, Punjab, Pakistan.
Fatima Amjad University of Punjab, Lahore, Punjab, Pakistan.
Naeem Haider Punjab College, Vehari, Punjab, Pakistan.

DOI:

https://doi.org/10.70749/ijbr.v2i02.146

Keywords:

Artificial Intelligence, Machine Learning, Metabolomics, Predictive Modeling, Disease Profiling,, Pancreatic Cancer, Clinical Applications

Abstract

With an emphasis on the identification of biomarkers for pancreatic cancer, this research investigated the use of artificial intelligence (AI) and machine learning (ML) in metabolomics for disease profiling. With the use of the Kaggle dataset "Pancreatic Cancer Urine Biomarkers," which comprises 591 samples from diverse patient cohorts, we examined the connections between distinct proteome and metabolomic markers and their diagnostic value. Plasma CA19-9, LYVE1, REG1B, REG1A, and TFF1 were among the key biomarkers that were assessed in order to create a prediction model that could differentiate between benign cases, healthy controls, and pancreatic ductal adenocarcinoma (PDAC). According to our findings, the XGBoost classifier performed much better than conventional statistical techniques, recognizing positive instances with 89% accuracy and 91% sensitivity. The research also demonstrated the intricate relationships between several biomarkers that affect diagnostic accuracy and emphasized the crucial significance of the REG1B/REG1A ratio as a new predictor. We verified our model's robustness and generalisability across various patient demographics using a thorough validation procedure that included cross-validation and sensitivity analysis. "This work demonstrates how artificial intelligence can revolutionize metabolomics, opening the door to more accurate illness characterization and individualized treatment plans. In order to enhance early identification and outcomes of pancreatic cancer and other associated disorders, our results ultimately support the use of machine learning techniques into clinical practice.

Downloads

Download data is not yet available.

References

Aksenov, A. A., da Silva, R., Knight, R., Lopes, N. P., & Dorrestein, P. C. (2017). Global chemical analysis of biology by mass spectrometry. Nature Reviews Chemistry, 1(7), 1–16. https://doi.org/10.1038/s41570-017-0034

Bifarin, O., Aleidan, F. A. S., Bistline, A., Abdalla, R. A., Atena, F., Obed, B. A., ... & Abou-Donia, M. (2021). Evaluation of Renal Cell Carcinoma metabolite biomarkers through advanced machine learning and metabolomics. Journal of Proteome Research, 20(3), 1611-1622. https://doi.org/10.1021/acs.jproteome.1c00213

Bujak, R., Struck-Lewicka, W., Markuszewski, M. J., & Kaliszan, R. (2015). Metabolomics for laboratory diagnostics. Journal of Pharmaceutical and Biomedical Analysis, 113, 108–120. https://doi.org/10.1016/j.jpba.2015.04.016

Caspersen, C., et al. (2005). Metabolomics in Alzheimer’s disease: Identifying metabolic biomarkers for early diagnosis. Journal of Alzheimer's Disease, 8(4), 427-432.

Chaganti, V., Kim, D. H., & Lee, S. I. (2021). Recent advances in machine learning for metabolomics and multi-omics integration. Frontiers in Genetics, 12, 739944. https://doi.org/10.3389/fgene.2021.739944

di Meo, S. A., Loizzo, D., Pandolfo, S. D., et al. (2022). Metabolomic approaches for detection and identification of biomarkers and altered pathways in bladder cancer. International Journal of Molecular Sciences, 23(8), 5143. https://doi.org/10.3390/ijms23084173

Fiehn, O. (2002). Metabolomics—the link between genotypes and phenotypes. Plant Molecular Biology, 48(1–2), 155–171. https://doi.org/10.1023/A:1013713905833

Griffiths, W. J. (2008). Metabolomics, metabolite profiling, and lipidomics: Why and how? BioScience Horizons: The International Journal of Student Research, 1(2), 68–73. https://doi.org/10.1093/biohorizons/hzn009

Han, J., Kamber, M., & Pei, J. (2011). Data Mining: Concepts and Techniques (3rd ed.). Morgan Kaufmann.

Han, S., Van Treuren, W., Fischer, C. R., Merrill, B. D., DeFelice, B. C., Sanchez, J. M., ... & Sonnenburg, J. L. (2021). A metabolomics pipeline for the mechanistic interrogation of the gut microbiome. Nature, 595(7867), 415-420. https://doi.org/10.1038/s41586-021-037079

Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer Science & Business Media.

Kotsiantis, S. B., Zaharakis, I., & Pintelas, P. (2007). Supervised machine learning: A review of classification techniques. Emerging artificial intelligence applications in computer engineering, 160(1), 3-24.

Kuhn, M., & Johnson, K. (2013). Applied Predictive Modeling. Springer.

Lee, W. H., Hong, J., Park, S., & Choi, S. (2020). A machine learning approach to classify cancer subtypes using gene expression data: Integrating gene expression data with deep learning. BMC Medical Genomics, 13(1), 37. https://doi.org/10.1186/s12920-020-0677-4

Libbrecht, M. W., & Noble, W. S. (2015). Machine learning applications in genetics and genomics. Nature Reviews Genetics, 16(6), 321–332. https://doi.org/10.1038/nrg3920

Liu, J. J., Liu, S., Gurung, R. L., Ching, J., Kovalik, J. P., Tan, T. Y., & Lim, S. C. (2021). Integrative serum metabolomics and machine learning to predict early-onset diabetic kidney disease. Molecular Metabolism, 53, 101367. https://doi.org/10.1016/j.molmet.2021.101367

Loo, R. L., et al. (2013). Biomarker discovery in cardiovascular diseases: The use of metabolomics in clinical and translational research. Journal of Biomedicine and Biotechnology, 2013, 826392. https://doi.org/10.1155/2013/826392

Mayeux, R. (2004). Biomarkers: Potential uses and limitations. NeuroRx, 1(2), 182–188. https://doi.org/10.1602/neurorx.1.2.182

Newgard, C. B. (2012). Metabolomics and metabolic diseases: Where do we stand? Cell Metabolism, 15(4), 402-411. https://doi.org/10.1016/j.cmet.2012.03.005

Oh, J. H., Alexander, L. M., Pan, M., Schueler, K. L., Keller, M. P., Attie, A. D., ... & Walter, J. (2020). Dietary fructose and microbiota-derived metabolites modulate sucrose preference in mice. Cell Metabolism, 31(4), 809-826. https://doi.org/10.1016/j.cmet.2020.06.005

Pavlova, N. N., & Thompson, C. B. (2016). The emerging hallmarks of cancer metabolism. Cell Metabolism, 23(1), 27-47. https://doi.org/10.1016/j.cmet.2015.12.006

Shen, B., Yi, X., Sun, Y., Bi, X., Du, J., Zhang, C., ... & Guo, T. (2020). Proteomic and metabolomic characterization of COVID-19 patient sera. Cell, 182(1), 59-72. https://doi.org/10.1016/j.cell.2020.05.032

Tiedt, S., Brandmaier, S., Kollmeier, H., Duering, M., Artati, A., Adamski, J., ... & Dichgans, M. (2020). Metabolomic patterns in ischemic stroke. Annals of Neurology, 87(1), 18-29. https://doi.org/10.1002/ana.25859

Tomita, M., & Nishioka, T. (2006). Metabolomics: The frontier of systems biology. Springer.

Wu, D., et al. (2020). COVID-19 metabolomics and potential biomarkers for treatment response. Nature Medicine, 26(7), 1036-1043. https://doi.org/10.1038/s41591-020-0954-5

Xia, J., Broadhurst, D. I., Wilson, M., & Wishart, D. S. (2012). Translational biomarker discovery in clinical metabolomics: An introductory tutorial. Metabolomics, 8(1), 89-107. https://doi.org/10.1007/s11306-011-0337-3